Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

awesome-tensorflow-lite

An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.
https://github.com/margaretmz/awesome-tensorflow-lite

Last synced: 5 days ago
JSON representation

Models with samples
- Computer vision
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - download
  - Codelab
  - Android
  - Colab Notebook - Sign-Language-Detection) | Community |
  - Colab Notebook - Sign-Language-Detection) | Community |
  - download - classifier) \| [tutorial 1](https://medium.com/swlh/icon-classifier-with-tflite-model-maker-9263c0021f72) \| [tutorial 2](https://medium.com/@margaretmz/icon-classifier-android-app-1fc0b727f761) | Community |
  - download
  - download
  - Paper - optimization/) | MobileDet is from University of Wisconsin-Madison and Google and the blog post is from the Community |
  - (download) - License) | Community |
  - download - cv4arvr/blazeface) | MediaPipe |
  - FaceNet - Authentication-App) | Community |
  - download - demo-hand-detection) | MediaPipe & Community |
  - download - TFLite-Image-Segmentation) \| [Realtime](https://github.com/kshitizrimal/tflite-realtime-flutter) \| [Paper](https://arxiv.org/abs/1706.05587) | tf.org & Community |
  - DeepLab V3 models - type=image-segmentation&publisher=sayakpaul) with Colab Notebooks | Community |
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Download - cv4arvr/hair-segmentation) | MediaPipe |
  - Arbitrary image stylization
  - models - style-transfer) \| [Android](https://github.com/margaretmz/segmentation-style-transfer/tree/master/android) \| [Tutorial](https://medium.com/google-developer-experts/image-background-stylizer-part-1-project-intro-d68c4547e7e3) | Community |
  - download
  - download - Game-Control-using-Pose-Classification-and-TensorFlow-Lite) | Community |
  - Models on TF Hub - TFLite) \| [Original Paper](https://arxiv.org/pdf/2003.06792v2.pdf) \| [Flutter](https://github.com/sayannath/MIRNet-Flutter)| | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - U-GAT-IT - with-tflite) \| [Android](https://github.com/margaretmz/selfie2anime-with-tflite/tree/master/android) \| [Tutorial](https://medium.com/google-developer-experts/selfie2anime-with-tflite-part-1-overview-f97500800ffe) | Community |
  - White-box CartoonGAN - model/cartoongan/dr/1)) | [Project repo](https://github.com/margaretmz/Cartoonizer-with-TFLite) \| [Android](https://github.com/margaretmz/Cartoonizer-with-TFLite/tree/master/android) \| [Tutorial](https://blog.tensorflow.org/2020/09/how-to-create-cartoonizer-with-tf-lite.html) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - YOLOv5 - v5-tflite-model) | Community |
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - TF Hub
  - Dynamic range models - implementation-of-video-style-transfer-with-tensorflow-lite-models-9338a6d2a3ea) | Community |
  - TF Hub - in-TensorFlow-Lite/blob/master/Boundless_TFLite.ipynb) \| [Original Paper](https://arxiv.org/pdf/2003.06792v2.pdf) | Community |
  - Models on TF Hub
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - DeepLab V3 model - camerax-with-image-segmentation-android-project-d8656f35cea3) | Community |
  - Flutter
  - Flutter
- Text
  - Android
  - Android
  - Download
  - Paper - Conversion to TFLite](https://tulasi.dev/craft-in-tflite) \| [Blog2-EAST vs CRAFT](https://sayak.dev/optimizing-text-detectors/) \| [Models on TF Hub](https://tfhub.dev/tulasiram58827/lite-model/craft-text-detector/dr/1) \| Android (Coming Soon) | Community |
  - Paper - model/east-text-detector/dr/1) \| [Conversion and Inference Notebook](https://colab.research.google.com/github/sayakpaul/Adventures-in-TensorFlow-Lite/blob/master/EAST_TFLite.ipynb) | Community |
  - Paper - Conversion to TFLite](https://tulasi.dev/craft-in-tflite) \| [Blog2-EAST vs CRAFT](https://sayak.dev/optimizing-text-detectors/) \| [Models on TF Hub](https://tfhub.dev/tulasiram58827/lite-model/craft-text-detector/dr/1) \| Android (Coming Soon) | Community |
- Speech
  - Reference
  - Android
  - Inference Notebook
  - Inference - asr) | Community |
- Recommendation
  - Dual-Encoder - device_recommendation_tflite) \| [Reference](https://blog.tensorflow.org/2020/09/introduction-to-tflite-on-device-recommendation.html) | tf.org & Community |
- Game
  - Flutter
Past announcements:
- Announcement of the new converter - [MLIR](https://medium.com/tensorflow/mlir-a-new-intermediate-representation-and-compiler-framework-beba999ed18d)-based and enables conversion of new classes of models such as Mask R-CNN and Mobile BERT etc., supports functional control flow and better error handling during conversion. Enabled by default in the nightly builds\.
- Android Support Library - Makes mobile development easier ([Android](https://github.com/tensorflow/examples/blob/master/lite/examples/image_classification/android/EXPLORE_THE_CODE.md) sample code).
- Model Maker - Create your custom [image & text](https://github.com/tensorflow/examples/tree/master/tensorflow_examples/lite/model_maker) classification models easily in a few lines of code. See below the Icon Classifier for a tutorial by the community.
- On-device training - It is finally here! Currently limited to transfer learning for image classification only but it's a great start. See the official [Android](https://github.com/tensorflow/examples/blob/master/lite/examples/model_personalization/README.md) sample code and another one from the community ([Blog](https://aqibsaeed.github.io/on-device-activity-recognition) | [Android](https://github.com/aqibsaeed/on-device-activity-recognition)).
- Hexagon delegate - How to use the Hexagon Delegate to speed up model inference on mobile and edge devices. Also see blog post [Accelerating TensorFlow Lite on Qualcomm Hexagon DSPs](https://blog.tensorflow.org/2019/12/accelerating-tensorflow-lite-on-qualcomm.html).
- Model Metadata - Provides a standard for model descriptions which also enables [Code Gen and Android Studio ML Model Binding](https://www.tensorflow.org/lite/inference_with_metadata/codegen).
- Model Metadata - Provides a standard for model descriptions which also enables [Code Gen and Android Studio ML Model Binding](https://www.tensorflow.org/lite/inference_with_metadata/codegen).
- Announcement of the new converter - [MLIR](https://medium.com/tensorflow/mlir-a-new-intermediate-representation-and-compiler-framework-beba999ed18d)-based and enables conversion of new classes of models such as Mask R-CNN and Mobile BERT etc., supports functional control flow and better error handling during conversion. Enabled by default in the nightly builds\.
Model zoo
- TensorFlow Lite models
  - MobileNet - Pretrained MobileNet v2 and v3 models.
  - TensorFlow Lite models - With official Android and iOS examples.
  - Pretrained models - Quantized and floating point variants.
  - TensorFlow Hub - Set "Model format = TFLite" to find TensorFlow Lite models.
  - Pretrained models - Quantized and floating point variants.
- TensorFlow models
  - TensorFlow models - Official TensorFlow models.
  - Tensorflow detection model zoo - Pre-trained on COCO, KITTI, AVA v2.1, iNaturalist Species datasets.
ML Kit examples
- TensorFlow models
  - ML Kit
  - ML Kit Translate demo - A tutorial with material design [Android](https://github.com/googlecodelabs/mlkit-android/tree/master/translate) (Kotlin) sample - recognize, identify Language and translate text from live camera with ML Kit for Firebase.
  - Computer Vision with ML Kit - Flutter In Focus
  - Flutter + MLKit: Business Card Mail Extractor - A blog post with a [Flutter](https://github.com/DaemonLoki/Business-Card-Mail-Extractor) sample code.
  - From TensorFlow to ML Kit: Power your Android application with machine learning - A talk with [Android](https://github.com/xebia-france/magritte) (Kotlin) sample code.
  - Building a Custom Machine Learning Model on Android with TensorFlow Lite
  - ML Kit and Face Detection in Flutter
  - ML Kit on Android 4: Landmark Detection
  - ML Kit on Android 3: Barcode Scanning
  - ML Kit on Android 2: Face Detection
  - ML Kit on Android 1: Intro
  - Computer Vision with ML Kit - Flutter In Focus
Plugins and SDKs
- TensorFlow models
  - Edge Impulse - Created by [@EdgeImpulse](https://twitter.com/EdgeImpulse) to help you to train TensorFlow Lite models for embedded devices in the cloud.
  - Coral Edge TPU - Edge hardware by Google. [Coral Edge TPU examples](https://coral.ai/examples/).
  - MediaPipe - A cross platform (mobile, desktop and Edge TPUs) AI pipeline by Google AI. (PM [Ming Yong](https://twitter.com/realmgyong)) | [MediaPipe examples](https://mediapipe.readthedocs.io/en/latest/examples.html).
Helpful links
- TensorFlow models
  - AI benchmark - A website for benchmarking computer vision models on smartphones.
  - Performance measurement - How to measure model performance on Android and iOS.
  - Material design guidelines for ML - How to design machine learning powered features. A good example: [ML Kit Showcase App](https://github.com/firebase/mlkit-material-android).
  - The People + AI Guide book - Learn how to design human-centered AI products.
  - TensorFlow Lite for Microcontrollers
  - Netron - A tool for visualizing models.
Learning resources
- Blog posts
  - Optical character recognition with TensorFlow Lite: A new example app
  - YOLOv3 to TensorFlow Lite Conversion - By Nitin Tiwari.
  - What is new in TensorFlow Lite - By Khanh LeViet.
  - Optimizing style transfer to run on mobile with TFLite - By Khanh LeViet and Luiz Gustavo Martins.
  - How TensorFlow Lite helps you from prototype to product - By Khanh LeViet.
  - Getting Started with ML on MCUs with TensorFlow - By Brandon Satrom.
  - TensorFlow Model Optimization Toolkit — float16 quantization halves model size - By the TensorFlow team.
  - Training and serving a real-time mobile object detector in 30 minutes with Cloud TPUs - By Sara Robinson, Aakanksha Chowdhery, and Jonathan Huang.
  - Why the Future of Machine Learning is Tiny - By Pete Warden.
  - Using TensorFlow Lite on Android - By Laurence Moroney.
  - https://blog.tensorflow.org/2021/06/easier-object-detection-on-mobile-with-tf-lite.html
- Books
  - AI and Machine Learning On-Device Development - By Laurence Moroney ([@lmoroney](https://twitter.com/lmoroney)).
  - AI and Machine Learning for Coders - By Laurence Moroney ([@lmoroney](https://twitter.com/lmoroney)).
  - Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter - world projects to implement end-to-end neural networks on Android and iOS ([GitHub](https://github.com/PacktPublishing/Mobile-Deep-Learning-Projects)) - By Anubhav Singh ([@xprilion](https://github.com/xprilion)) and Rimjhim Bhadani ([@Rimjhim28](https://github.com/Rimjhim28)).
  - Complete Bundle - of-contents-raspberry-pi-for-computer-vision/)) - By the PyImageSearch Team: Adrian Rosebrock ([@PyImageSearch](https://twitter.com/PyImageSearch)), David Hoffman, Asbhishek Thanki, Sayak Paul ([@RisingSayak](https://twitter.com/RisingSayak)), and David Mcduffee.
  - TinyML - By Pete Warden ([@petewarden](https://twitter.com/petewarden)) and Daniel Situnayake ([@dansitu](https://twitter.com/dansitu)).
  - Practical Deep Learning for Cloud, Mobile, and Edge - By Anirudh Koul ([@AnirudhKoul](https://twitter.com/AnirudhKoul)), Siddha Ganju ([@SiddhaGanju](https://twitter.com/SiddhaGanju)), and Meher Kasam ([@MeherKasam](https://twitter.com/MeherKasam)).
- Videos
- Podcasts
  - Talking Machine Learning with Hoi Lam
- MOOCs
  - Introduction to TensorFlow Lite - Udacity course by Daniel Situnayake (@dansitu), Paige Bailey ([@DynamicWebPaige](https://twitter.com/DynamicWebPaige)), and Juan Delgado.
  - Device-based Models with TensorFlow Lite - Coursera course by Laurence Moroney ([@lmoroney](https://twitter.com/lmoroney)).
  - The Future of ML is Tiny and Bright - A series of edX courses created by Harvard in collaboration with Google. Instructors - Vijay Janapa Reddi, Laurence Moroney, and Pete Warden.
Ideas and Inspiration
- TensorFlow models
  - E2E TFLite Tutorials - Checkout this repo for sample app ideas and seeking help for your tutorial projects. Once a project gets completed, the links of the TensorFlow Lite model(s), sample code and tutorial will be added to this awesome list.

Programming Languages

Python 2 JavaScript 1 C++ 1 Jupyter Notebook 1

Ecosyste.ms: Awesome

awesome-tensorflow-lite

Models with samples

Computer vision

Text

Speech

Recommendation

Game

Past announcements:

Model zoo

TensorFlow Lite models

TensorFlow models

ML Kit examples

TensorFlow models

Plugins and SDKs

TensorFlow models

Helpful links

TensorFlow models

Learning resources

Blog posts

Books

Videos

Podcasts

MOOCs

Ideas and Inspiration

TensorFlow models